]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 49662cb)
llama : restore intended k-quants mixes for MoE models (#4872)
authorKawrakow <redacted>
Thu, 11 Jan 2024 19:43:15 +0000 (20:43 +0100)
committerGitHub <redacted>
Thu, 11 Jan 2024 19:43:15 +0000 (21:43 +0200)
commit469e75d0a35b08de549a4fd87f082ca7a8a539ba
tree39969cc5ba3c124a5464f1a2ec177429bf4c516etree
parent49662cbed3e95f5976c070b85b9fd53fd577038dcommit | diff
llama : restore intended k-quants mixes for MoE models (#4872)

* Restore intended k-quants quantization mixes for MoE models

* Update Q2_K_S values in the quantize tool

Still using LLaMA-v1 PPL values in the quant description
today does not make much sense. But let's leave this update
for another PR.

---------

Co-authored-by: Iwan Kawrakow <redacted>
Co-authored-by: Georgi Gerganov <redacted>
examples/quantize/quantize.cpp diff | blob | history
llama.cpp diff | blob | history
llama.h diff | blob | history
Packaging of ggml-org/llama.cpp